I've been looking more and more at running my own models in projects where OpenAI becomes restrictively expensive, now I can test and compare outputs easily.

I've been looking more and more at running my own models in projects where OpenAI becomes restrictively expensive, now I can test and compare outputs easily. 

https://jan.ai/

Practical AI fanatic. CTO & Founder. Open-Source Maxi. Good Cook, Mediocre Bowler.

https://legacy.donotresearch.net/authors/jeremiah-currier

and 🚂 /trains

missed this! one theme I'm diving into is continuous processing, anything that you're trying to run for as close to 24/day as possible. For ex, financial market analyst

another more concrete - "calling API with maximum throughput over large set of data with advanced models i.e. gpt-4 can get EXPENSIVE IN JUST SECONDS"

another more concrete - "calling API with maximum throughput over large set of data with advanced models i.e. gpt-4 can get EXPENSIVE IN JUST SECONDS"

https://github.com/lion-agi/lionagi

Any examples / themes you can share of projects that got too expensive?

parenting, kidlit, protocols, travel, china, humor, hardcore, pizza, kpop ➔ hosting /melon /y2k author of /trending-casts

love how easy it is to download models locally.